fix(gat): stack y_prob via numpy before torch.tensor#17
Merged
protosphinx merged 1 commit intomainfrom Apr 29, 2026
Merged
Conversation
…onversion warning) `torch.tensor(list_of_numpy_arrays)` walks every element through Python on the conversion path, which on real-sized BPI logs is meaningfully slower (~10x in the original measurement) than stacking with numpy first. PyTorch even prints an "extremely slow" warning. Switch to `torch.from_numpy(np.stack(...))` and guard the empty-list case. Credit: spotted and originally fixed in #8 by @adamya-singh; reapplied on top of the audit refactor since the original PR conflicted with the node-level head.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Re-applies the optimization originally proposed by @adamya-singh in #8 on top of the post-audit code (which had drifted enough that #8 conflicted).
torch.tensor(list_of_numpy_arrays)walks every element through Python; stacking with numpy first is ~10× faster on real validation sets and silences the "extremely slow" PyTorch warning.Closes #8 once merged.